kumo@1.0

Reasoning

KUMO full dataset (5300 tasks; 50 instances per scenario).

← Back to Registry

Run this task

CLI:

inspect eval inspect_harbor/kumo_1_0 --model openai/gpt-5

Python:

from inspect_ai import eval
from inspect_harbor import kumo_1_0

eval(kumo_1_0(), model="openai/gpt-5")

Dataset information

Harbor registry kumo@1.0
Inspect task kumo_1_0
Version 1.0
Samples 5300

See Task Parameters for the parameter set shared across all Harbor tasks.